Online Observer-Based Inverse Reinforcement Learning

11/03/2020
by   Ryan Self, et al.
0

In this paper, a novel approach to the output-feedback inverse reinforcement learning (IRL) problem is developed by casting the IRL problem, for linear systems with quadratic cost functions, as a state estimation problem. Two observer-based techniques for IRL are developed, including a novel observer method that re-uses previous state estimates via history stacks. Theoretical guarantees for convergence and robustness are established under appropriate excitation conditions. Simulations demonstrate the performance of the developed observers and filters under noisy and noise-free measurements.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/04/2021

Hybrid Adversarial Inverse Reinforcement Learning

In this paper, we investigate the problem of the inverse reinforcement l...
11/12/2020

Imposing Robust Structured Control Constraint on Reinforcement Learning of Linear Quadratic Regulator

This paper discusses learning a structured feedback control to obtain su...
10/29/2019

Feedback Linearization for Unknown Systems via Reinforcement Learning

We present a novel approach to control design for nonlinear systems, whi...
09/24/2017

An Optimal Online Method of Selecting Source Policies for Reinforcement Learning

Transfer learning significantly accelerates the reinforcement learning p...
10/06/2020

Reinforcement Learning in Deep Structured Teams: Initial Results with Finite and Infinite Valued Features

In this paper, we consider Markov chain and linear quadratic models for ...
05/04/2020

Noise Pollution in Hospital Readmission Prediction: Long Document Classification with Reinforcement Learning

This paper presents a reinforcement learning approach to extract noise i...
05/21/2018

A Framework and Method for Online Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) is the problem of learning the pref...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.